{"id":"W7106817928","doi":"10.48448/7va5-5c32","title":"DAVIS: Planning Agent with Knowledge Graph-Powered Inner Monologue","year":2025,"lang":"","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Key (lock); Benchmark (surveying); Intelligent agent; Scientific reasoning; Term (time)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007293611,0.0009291455,0.000425926,0.0005445402,0.0006334381,0.00138673,0.002212071,0.001558324,0.01600068],"category_scores_gemma":[0.003338504,0.0004101322,0.0007101301,0.0003581851,0.000854809,0.002485977,0.002667882,0.001147328,0.004559487],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008295794,"about_ca_system_score_gemma":0.001727107,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008158525,"about_ca_topic_score_gemma":0.01528184,"domain_scores_codex":[0.9994907,0.0001500575,0.00003279966,0.0001748052,0.0001077213,0.00004392722],"domain_scores_gemma":[0.9992962,0.0003100723,0.00003771222,0.0001902094,0.00008829443,0.00007751326],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008924028,0.0007947879,0.002659789,0.0009988587,0.0001868376,0.001203121,0.001120777,0.1963075,0.01967956,0.09090175,0.1550294,0.5302252],"study_design_scores_gemma":[0.0003252955,0.0002292686,0.000304461,0.00005484388,0.00007331178,0.0002972851,0.0002495118,0.8039496,0.0119873,0.05859164,0.1238712,0.00006626871],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02961997,0.001184603,0.8329805,0.001789761,0.0003964932,0.0007441739,0.003530136,0.07749827,0.05225608],"genre_scores_gemma":[0.3152049,0.0004363807,0.640397,0.0009487837,0.00006524119,0.0005629906,0.007240717,0.001673051,0.03347097],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01600068,"threshold_uncertainty_score":0.05352765,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05448810703700743,"score_gpt":0.3405678502634193,"score_spread":0.2860797432264119,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}